← LLM

Alibaba

qwen-turbo

Measured 2026-10-04

Run qwen-turbo on Speko →

One API, every model on this board.

Score

52

Task done

30.61%

12–52% 95% CI bootstrap over items · n=95 · measured 2026-10-04

Refusal quality

11.1%

names the gap 0% · offers a route 10% · 10 probes x 3 iterations · 3 silent turns scored zero

Fabrication

90%

27 of 30 probe runs

Dead-air

32.9%

49 of 149 turns

Tool silence

100.0%

all of 10 items (49 tool-call turns) · ≥69%

Stalled

72.2%

65 of 90 runs

TTFT p50

430ms

430–544 p50–p90 · n=38

Cost / 1M tok

$0.20

Share this result

Embed the live badge

Speko llm rank
Markdown
[![Speko llm rank](https://benchmarks.speko.ai/badge/llm/alibaba-qwen-turbo.svg)](https://benchmarks.speko.ai/llm/alibaba-qwen-turbo)
HTML
<a href="https://benchmarks.speko.ai/llm/alibaba-qwen-turbo"><img src="https://benchmarks.speko.ai/badge/llm/alibaba-qwen-turbo.svg" alt="Speko llm rank"></a>
URL
https://benchmarks.speko.ai/llm/alibaba-qwen-turbo